SikuliX

ocr

Asked by sanjana

Is there a way to improve the text recognition in sikuli by training the images using tessaract tool???
Can you tel me the procedure to go ahead with training the images using tessaract......

Question information

Language:
English Edit question
Status:
Answered
For:
SikuliX Edit question
Assignee:
No assignee Edit question
Last query:
Last reply:
Revision history for this message
RaiMan (raimund-hocke) said : 		#1

I cannot help you with Tesseract itself and the training feature.
But the net has surely enough tutorials on that.
You might give it a try and replace/add the generated stuff to Sikuli's tessdata folder.

Revision history for this message
Carlos Garcia (calgarcia) said : 		#2

Hello RaiMan, following your instructions above, may conclude that to appply a new trainned language to Sikuli, all we need is to overwrite the folder tessdata with the files from the new language? Thanks a lot.

Revision history for this message
RaiMan (raimund-hocke) said : 		#3

@Carlos
principally yes - but I do not have any experience yet.

Revision history for this message
Carlos Garcia (calgarcia) said : 		#4

Thanks for your quick response. I'm going to use sikuli here at Brazil to automate tests but using my own intarfce not Sikuli Interface. As we use the portuguese language I'll need a lot of trainning tasks to get success on text recognizing. Thanks very much.

Can you help with this problem?

Provide an answer of your own, or ask sanjana for more information if necessary.

To post a message you must log in.